arXiv Machine Learning
The Metagame of Interpretability and Meta-Attributions
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 1
Integrating attention into explanation frameworks for language and vision transformers
arXiv:2508.08966v2 Announce Type: replace Abstract: The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a gro...
arXiv Machine Learning
Jun 3
Attribution via Distributional Paths for Information Revelation
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
arXiv Machine Learning
Aug 28
The Attribution Contract for Generative Language Models
The paper argues that feature attribution scores for generative language models lack a fixed meaning because each generated token is both output and input, leading to multiple distinct explanatory questions. It introduces the Attribution Contract framework, which explicitly defines the model score, fixed variables, target output, generation process, and eligible features, showing how these choices affect attribution outcomes. Experiments demonstrate that different contracts (e.g., local next-token vs. prompt-level) and model architectures (mixture-of-experts vs. masked-diffusion) yield markedly different attribution distributions, highlighting the need for careful contract specification.
arXiv AI
Aug 5
Which Modality Decides? Counterfactual Modality Attribution for Multimodal LLMs
arXiv:2608. 00076v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text.
arXiv AI
Sep 25
Every Component Is a Lookup: One Linear Graph for Interaction, Composition and Attribution
The paper proposes that two architectural assumptions—(1) attention and MLPs share a key‑value form <phi(S)>U, and (2) components read from an additive residual stream—are sufficient to answer three interpretability questions: component interaction, information routing, and token attribution. By treating these selections as a computational graph, the authors develop Unpack, a backward attribution method that validates interaction scores, recovered routes, and token attribution against established tests across models ranging from 160M to 6.9B parameters. The study also shows that contribution and causal effect can differ, with a recognizable signature in how components change when a task is removed.
arXiv Machine Learning
Sep 10
I Don't Miss You, but I Do: Self-Explanation Faithfulness of Modality Missingness in Vision-Language Models
The paper introduces an interventional protocol to assess how vision‑language models (VLMs) explain the impact of missing modalities on their predictions. By comparing the models’ self‑explanations with actual changes observed after restoring missing inputs, the study finds that VLMs routinely overstate the sufficiency of available evidence and underestimate the effect of adding back missing modalities. Across eight open‑weight VLMs and four tasks, the discrepancy between predicted and realized changes is substantial, revealing systematic mischaracterization of modality dependence.